Triple
T22895240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Letter XII |
E568154
|
entity |
| Predicate | hasWorkTitleInCollection |
P2011
|
FINISHED |
| Object | Letter XII from a Farmer in Pennsylvania |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Letter XII from a Farmer in Pennsylvania | Statement: [Letter XII, hasWorkTitleInCollection, Letter XII from a Farmer in Pennsylvania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkTitleInCollection Context triple: [Letter XII, hasWorkTitleInCollection, Letter XII from a Farmer in Pennsylvania]
-
A.
hasTitleWork
Indicates that an entity is associated with a specific work by its title (i.e., the entity has or bears that work’s title).
-
B.
hasWorkInCollection
chosen
Indicates that a work or item is included as part of a particular collection.
-
C.
hasWorkingTitle
Indicates that an entity is associated with a provisional or temporary title used during its development or production.
-
D.
hasWorkTitlePattern
Indicates that an entity’s work title follows or matches a specified pattern or structured format.
-
E.
hasWorkingTitleStatus
Indicates that an entity currently holds the status of having a provisional or working title rather than a finalized official title.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc83d688190a8ab5ea0aad1e7ec |
completed | April 29, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69ef3b6b2e2481908258156937b5a745 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:40 p.m.